In a rational multi-criteria decision-making (MCDM) process based on multi-attribute utility theory (MAUT), the decision-maker defines quantitative parameters to identify the most promising alternative. However, it is often difficult to determine these parameters precisely. Therefore, the literature suggests using imprecise information, which allows the decision-maker to determine imprecise preference statements and parameters. This paper investigates the utilization and impact of an imprecise information approach regarding probabilities, utility functions, and objective weights in the decision support system Entscheidungsnavi. We examined 1511 personal student decisions. First, we analyzed how often imprecise information was utilized. Second, we surveyed how helpful participants found the use of imprecise information. Third, we investigated the impact of imprecise information in the three aforementioned categories on the final ranking of alternatives. We assessed how robust the rank of the best alternative remained by using Monte Carlo simulations in which evenly distributed values were drawn from all imprecisely defined intervals. This demonstrates the robustness of our results across varying levels of input uncertainty. Most participants chose imprecise parameters in their decisions. Moreover, most participants found it helpful to use imprecise information in all categories, with imprecise objective weights being the least helpful. In about 83% of the decisions, the best-ranked alternative is robust against the imprecise intervals the decision-maker chooses. Overall, our results show that incorporating imprecision improves the practical usefulness of MCDM-Support-Systems. We recommend that a robust MAUT-based system should address all three types of imprecision, guide probability and utility elicitation, support realistic trade-offs, and visualize how input uncertainty affects ranking stability helping decision-makers form sound judgements.
This study presents a novel two commodity stochastic retrial inventory model tailored to handle batch demands while incorporating an innovative incentive mechanism to manage customer behavior and demand fluctuations. The model considers two distinct customer classes, each primarily interested in one of two commodities, with demand occurring in batches. A conditional complementary item policy is introduced to encourage larger purchases and foster cross-selling opportunities reflecting real-world marketing strategies. The inventory system is formulated as a level-dependent quasi-birth-and-death process. An (s,S1) inventory replenishment policy is applied to the primary commodity, while the secondary commodity is assumed to be replenished instantaneously. To analyze the system’s steady-state behavior, the Neuts and Rao matrix truncation method is applied, enabling the derivation of stability conditions and performance measures. Comprehensive numerical analysis is performed to optimize total cost and investigate the sensitivity of critical factors, such as expected total cost, customer waiting time, and successful retrial rate. Additionally, a detailed simulation study is conducted to validate the analytical findings, demonstrating the model’s effectiveness in real-world scenarios by capturing stochastic variations and system dynamics that may not be fully addressed through analytical methods alone. The simulation results provide further insights into the model’s robustness and practical applicability. This research advances the field of multi-commodity inventory systems, offering a valuable framework for optimizing inventory strategies in complex, interconnected market environments.
This study proposes a hybrid multi-criteria decision-making method for purchasing electric vehicles, by combining the analytic hierarchy process (AHP) with the evaluation based on distance from the average solution (EDAS). AHP assigns criteria weights and derives the scores for qualitative criteria, while the technical specifications of the electric vehicles are considered as the decision data for quantitative criteria. EDAS is employed to rank the electric vehicles and determine the best option, based on the appraisal scores that indicate the overall performance of each vehicle, relative to that of the average solution. The proposed method is implemented for making electric-vehicle purchase decisions, in Thailand, based on real-world data and decision-makers’ perspectives. The findings reveal that the proposed method can make effective electric-vehicle purchase decisions. It straightforwardly elicits the decision-makers’ needs through criteria weights; the decision-makers place high emphasis on the comfort criterion, with a weight of 0.176. Furthermore, the proposed method successfully ranks all electric vehicles and appropriately identifies the best electric vehicle, with an appraisal score of 0.749, which demonstrates superior overall performance across all decision-making attributes. The theoretical novelty of this study lies in the ability of the proposed method to reflect the decision-makers’ judgments, analyze both quantitative and qualitative criteria, and systematically derive the best decision. This study offers practical benefits to consumers, manufacturers, and government agencies, by supporting electric-vehicle purchase decisions, guiding the development of new electric-vehicle models, and informing policy formulations to promote electric-vehicle adoption.
This critical review analyzed 118 articles applying multicriteria decision analysis (MCDA) to environmental problems that were published in operational research (OR) journals. Main aim was to evaluate whether OR research is adequately treating real-world decision processes. Research questions emerged from analyzing 34 review articles covering mainly environmental literature. In contrast to this applied literature, results indicate that the field of OR is strong in uncertainty treatment. However, advanced modelling and analysis of temporal or spatial aspects was rare. Documentation of MCDA processes was often sketchy. Stakeholder engagement throughout decision-making processes was low. Main steps of MCDA were neglected, ranging from problem structuring, over preference elicitation, to discussing results with stakeholders. Future OR research could contribute substantially to solving todays’ pressing environmental problems by (i) improving applications to real-world decision processes; (ii) developing methods of stakeholder engagement and integrating soft-OR methods; (iii) applying behavioral OR for analyzing decision processes; (iv) supporting real-world implementation after MCDA; and (v) linking efforts across disciplines for proper documentation of practice interventions.
This study explores the role of specific design documents - as visual artefacts - in shaping decision-making processes, highlighting how they can, at key moments, overcome conflicts by negotiating different perspectives. Architectural design research has undergone significant paradigm shifts, primarily through traditional sociological and anthropological approaches to professional practices in engineering and architecture. While scholars have examined how practitioners operate and how practices unfold, they have yet to connect the specific performativity of each artefact within these processes to its effects. Focusing on practices, the research follows different strands of research. First, it draws on Actor-Network Theory (ANT) and recent ethnographies of architecture. Second, it links such perspective to Problem Structuring Methods (PSMs), focusing on interactions through artefacts. Finally, it contributes to a current debate in organization studies on the role of artefacts as boundary objects. Accordingly, the paper explores the role of architectural design practices in bringing forward effects in the decision-making process of a masterplan for developing an urban university campus. This paper makes a threefold contribution. First, in theoretical terms, tracing the performativity of architectural design practices. Second, in methodological terms, proposing a mapping methodology to trace such practices. Finally, it provides an interactive visualization tool.
This research investigates the variability of decision-making preferences, represented in terms of decision rules and criteria weights, in the context of the qualitative multi-criteria method DEX (Decision EXpert). We study the differences between decision rules acquired from different subjects (inter-personal differences) and from the same subjects at different times (intra-personal differences). We also assess the consistency of so-acquired rules and the ability of subjects to estimate the importance (weights) of criteria. The methodological approach consisted of two surveys among students, carried out about one and a half month apart. Four thematic areas were addressed in the questionnaires: selection of study programs, student success, car purchase decisions, and choices regarding everyday shopping venues. In both survey periods, participants were required to assess the importance of these criteria and to define decision rules according to the DEX method. The findings provide insights into the stability of decision-making processes among participants and in time. The results indicate a high variability of decision rules, both inter- and intra-personal. Intra-personal drift is lower than inter-personal differences, but not by much (three-quarters of the latter). The consistency of rules varied between small decision tables with clearly ordered criteria, where it was almost perfect, and large decision tables with less apparent preferential relations. Defining fully consistent decision tables turned out to be hard, indicating the need for automated consistencychecking tools. Criteria weights also drifted in time at the rate about 9% (user-provided weights) and 10-27% (weights assessed algorithmically from decision rules). The main contributions of this study are identified and quantified magnitudes of decision rules variability and consistency.
The development of Artificial Intelligence (AI) solutions for preventive maintenance applications is a risky and resource-demanding process. Typically, there are several candidate solutions whose performance in transforming data into useful prognostic information is initially uncertain. These uncertainties can be managed by structuring the development process into multiple stages that help choose and implement the final solution. In this paper, we propose such a stage-gate process by using Robust Portfolio Modelling to screen increasingly detailed candidate solutions through four development stages and three decision gates. The development stages generate evidence on how the candidate solutions contribute to six development objectives that represent different financial and technical criteria. At the decision gates, decisions about the continuation/termination of candidate solutions are taken by identifying portfolios of non-dominated candidate solutions subject to time and budget constraints. Uncertainties are captured by admitting incomplete information about the criteria weights and scores of candidate solutions. We illustrate the process by considering the development of an AI solution for a train’s toilet door system. The process brings consistency to the development process and, among other benefits, helps mitigate the risk of missing the development objectives due to premature fixation on a single candidate solution.
Small and Medium-sized Enterprises (SMEs) have traditionally relied on top-down planning approaches such as Manufacturing Resource Planning II (MRP II), which are increasingly inadequate in addressing the dynamic and uncertain environments shaped by Industry 4.0 and 5.0. These paradigms require organizations to continuously adapt by integrating heterogeneous data, fostering collaboration, and placing humans at the centre of decision-making processes. However, current research on supporting decision-making in SMEs within these contexts remains limited. This paper proposes a structured Group Decision Support System (GDSS) tailored to SMEs, combining a Multi-Criteria Decision-Making (MCDM) approach with a simulation-based planning model. The approach enables actors from different hierarchical levels (strategic, tactical, and operational) to express preferences, compute Key Performance Indicators (KPIs), and collaboratively evaluate alternatives. The approach emphasizes transparency and coherence in decision-making while addressing individual and collective priorities. A didactic case study involving the selection of delivery policies illustrates the applicability and benefits of the proposed approach, allowing users to explore trade-offs, simulate scenarios, and converge towards a shared strategic decision.
This paper presents a novel integration of machine learning and optimization techniques for robust supply chain network design under uncertainty, demonstrated through a regional coal distribution system (150 suppliers, 500 consumers, 7.5 million tonnes annually). Unlike traditional approaches that focus solely on cost minimization, our progressive methodology uniquely combines k-means clustering with mixed-integer programming to identify configurations that are both cost-effective and resilient to demand variability. Starting from a baseline singlewarehouse configuration costing $404.6 million annually, our approach systematically evaluates multi-facility alternatives through Monte Carlo simulation (50,000 iterations), revealing remarkable system stability-only 0.96 % cost variation despite 25 % individual volume uncertainty. The k-means analysis identifies optimal clustering patterns, while subsequent mixed-integer programming confirms that a five-warehouse configuration reduces annual transportation costs by 45.8 % ($185.3 million savings) while maintaining 90-100 % capacity utilization. This configuration demonstrates a Net Present Value of $3.02 billion over 50 years, significantly outperforming traditional single-facility designs. Critically, correlation analysis reveals that shipment volumes (rho=0.739) drive costs more than distances (rho=0.556), challenging conventional distance-minimization paradigms. The integrated framework is computationally efficient (4.2 s to optimality), scalable to larger networks, and applicable to various bulk commodity distribution challenges, offering supply chain managers a robust tool for strategic network design under uncertainty.
The concept of sustainable mobility is aimed at minimising environmental impacts of transportation systems while meeting the needs of individuals and communities. This includes encouraging citizens to choose sustainable modes of transportation: walking, cycling, public transport, carpooling, and telecommuting. We present an approach at rewarding organisations that actively support the sustainable mobility of their employees, and propose a framework for awarding a sustainable mobility certificate to organisations that fulfil sustainable mobility goals and objectives. The assessment is carried out using a qualitative rule-based multi-criteria model, which considers 50 indicators. Other elements of the certification process include methods for assessing the mobility structure of employees in the organisation and its potential for improvement. In this paper, we present the main components of the proposed certification framework and illustrate its application for assessing the status of sustainable mobility of employees at a Slovenian research institute.
In the context of advancing energy infrastructure, the planning and development of natural gas smart energy hubs have gained importance as essential components of sustainable energy systems. Thus, this paper introduces a portfolio selection model designed to improve the planning process for natural gas smart energy hubs. The proposed model integrates a multicriteria benefit-to-cost ratio-based (BCR) heuristic approach with surrogate weights and swing elicitation procedure, providing a robust framework for decision-makers to assess and prioritize investment options. The methodology encompasses a diverse set of criteria, including economic, environmental, and social factors, ensuring a holistic evaluation of candidate projects. A Decision Support System (DSS) called ROCSPort was proposed to operationalize and validate the proposed methodology, with a view to providing a streamlined preference modeling process for the decision-maker. The DSS also performs a sensitivity analysis based on a Monte-Carlo simulation approach, and statistical tests can be performed to verify the stability of the results. The model's applicability is demonstrated through a numerical application in a Brazilian energy company, illustrating its capacity to improve the selection of projects based on predefined objectives and constraints. The findings contribute to the energy planning context by offering a systematic and adaptable approach and tool for portfolio selection, aiding decision-makers involved in determining a sustainable energy infrastructure.
The cross-efficiency evaluation method is a powerful tool for assessing efficiency. However, previous research has often overlooked the bounded rationality of decision makers (DMs), thereby neglecting key factors. To address this gap, we investigate the cross-efficiency weight aggregation method under bounded rationality. Firstly, we develop a utility function incorporating inequality aversion and overconfidence, integrating them into the cross-efficiency weight aggregation process to formulate the equity-minded cross-efficiency method. Secondly, building upon this method, we address consensus issues within evaluation groups by introducing a consensus compromise algorithm. This algorithm aims to reconcile group opinions based on the principles of the equity-minded cross-efficiency approach. Furthermore, we apply our model to evaluate healthcare service efficiency in China. Our analysis explores the impact of overconfidence and fairness preferences, using a Tobit regression model to examine factors influencing healthcare service efficiency.
Recently, transportation problems in evolving cities have become increasingly complex thus requiring innovative solutions. The complexity arises from the combination of urbanization, technological advancements, and diverse demographics. Therefore, integrating advanced methodologies, such as machine learning (ML), into transportation planning becomes essential. This study explores the application of ML techniques to predict and understand tourists’ transport mode choices when engaging in leisure activities. A comparative analysis of various ML algorithms including Neural Networks, k-Nearest Neighbor (k-NN), Naive Bayesian, Decision Tree, Support Vector Machines, Discriminant Analysis, and Ensembles reveals distinctive strengths and trade-offs. Based on the results, Neural Networks demonstrate high accuracy, precision, recall, and specificity, which makes the algorithm well-suited to predict transport mode choices. While k-NN exhibits competitive precision and recall, it struggles with specificity and indicates a higher false positive rate. These findings support transportation planners to select the most suitable algorithm according to the desired outcomes. The adoption of these advanced approaches enhances the understanding of travel behavior thus offering valuable tools for developing efficient urban transportation systems.
Multi-Criteria Decision Analysis (MCDA) is a systematic approach to evaluating and prioritizing alternatives based on multiple, often conflicting, criteria. It integrates quantitative and qualitative data, expert judgment, and stakeholder input to support transparent and structured decision making. Recent advances in MCDA methodologies have been supported by the development of software tools that enhance their practical application. This paper presents PROMETHEE-Cloud, a web-based tool for applying the PROMETHEE methodologies. PROMETHEE-Cloud provides user-friendly interfaces for a range of functionalities such as sensitivity analysis, e.g., Monte Carlo simulations, Walking Weights, Insensitivity Intervals and supports the import/export of decision models. Furthermore, PROMETHEE-Cloud is used to evaluate sustainability measures for a container terminal. The results show the effectiveness of the tool in helping decision makers to identify and prioritize optimal solutions under multiple conflicting criteria.
E-banking offers clients unparalleled convenience but also exposes them to potential fraud from cyber criminals. Traditionally, banks use technical security measures to ameliorate these kinds of threats. These measures, while essential, are not universally efficacious in preventing fraud. It would be wise to augment technical measures with softer measures such as behavioural interventions (i.e., nudges). In this paper, we report on the effectiveness of behavioural nudges designed to dissuade opportunistic “others” from committing e-banking fraud. Here, we report on an investigation into the impact of the deployment of a number of behavioural nudges in an e-banking customer interface. We evaluated their impact through semi-structured interviews with e-banking customers in the United States of America. We found that nudges which emphasise empathy and heightened awareness of traditional security measures were remarkably effective in dissuading dishonesty. Notably, deployment immediately after login yielded optimal results. Our findings highlight the potential of behavioural nudges to reduce e-banking fraud, thereby augmenting traditional technical countermeasures. We conclude with recommendations for future research.
The generation of alternative policies is essential in complex decision tasks with multiple interests and stakeholders. A diverse set of policies is typically desirable to cover the range of options and objectives. Decision modelling literature has often assumed that clearly defined decision alternatives are readily available. This is not a realistic assumption in practice. We present a structured process model for the generation of policy alternatives in settings that include non-quantifiable elements and where portfolio optimisation approaches are not applicable. Behavioural issues and path dependence as well as heuristics and biases which can occur during the process are discussed. The behavioural experiment compares policy alternatives obtained by using two different portfolio generation techniques. The results of the experiment demonstrate that path dependence can occur in policy generation. We report thinking patterns of subjects which relate to biases and heuristics.
We consider multiobjective combinatorial optimization problems handled by preference-driven efficient heuristics. They look for the most preferred part of the Pareto front based on some preferences expressed by the user during the process. In general, the Pareto set of efficient solutions is searched for in this case. However, obtaining the Pareto set does not solve the decision problem since one or more solutions, being the most preferred for the user, have to be selected. Therefore, it is necessary to elicit their preferences. What we are proposing can be seen as one of the first structured methodologies in facility location problems to search for optimal solutions taking into account the preferences of the user. To this aim, we use an interactive evolutionary multiobjective optimization procedure called NEMO-II-Ch. It is applied to a real-world multiobjective location problem with many users and many facilities to be located. Several simulations have been performed. The results obtained by NEMOII-Ch are compared with those obtained by three algorithms knowing the user's "true" value function that is, instead, unknown to NEMO-II-Ch. They show that in many cases, NEMO-II-Ch finds the best subset of locations more quickly than the methods knowing the whole user's true preferences.
This study introduces a novel approach to effectively and efficiently solve Multi-Attribute Decision Making (MADM) problems with a considerable number of attributes. We demonstrate the need to categorize the attributes and facilitate a more systematic expert comparison. Our proposed method utilizes pairwise comparisons to assess attributes without requiring additional computations to evaluate the level of consistency. The proposed method offers greater flexibility and precision with reduced computational complexity. We present a comparative analysis with a widely used numerical example in the MADM literature to demonstrate the effectiveness and efficacy of the method proposed in this study.
Unincentivized measurement instruments of risk attitudes suffer from several weaknesses. One is that respondents do not consistently assign themselves to their respective risk preference categories. In particular, they are subject to a central tendency bias and classify themselves as risk-neutral when they are in fact not. We test the robustness of the central tendency bias in lottery-type questions for risk evaluations and offer an explanation of why respondents behave in a way that contradicts plausible utility models. We explore a wide range of alternative influencing factors, including careless responding, stake levels, deviations in expected value, the cognitive abilities of the respondents, self-assessment of risk attitudes, and monetary incentives. We find that careless responding and higher stakes increase the central tendency bias in risk assessment, while cognitive capabilities and extreme risk self-assessments (both positive and negative) decrease the bias. Deviations in expected value and incentives do not affect the bias. Our study further points to the fact that such problems have to be taken care of explicitly when eliciting risk attitudes.
